AJAbhik Jana

Abhik Jana

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Abhik Jana has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    TripTide: A Benchmark for Adaptive Travel Planning under Disruptions

    by Priyanshu Karmakar, Soumyabrata Chaudhuri, Shubhojit Mallick, Manish Gupta, Abhik Jana, Shreya Ghosh

    Recent efforts like TripCraft and TravelPlanner have advanced the use of Large Language Models ( LLMs) for personalized, constraint aware travel itinerary generation. Yet, real travel often faces disruptions. To address this, we present TripTide, the first benchmark evaluating LLM's ability to revise itineraries under realistic disruptions. TripTide models key dimensions such as disruption severity and traveler tolerance, enabling nuanced assessment of LLM adaptability to events like flight cancellations, weather closures, or overbooked attractions. We conduct a threefold evaluation. First, we introduce automatic metrics including Preservation of Intent (how well the revised plan maintains feasibility and goals), Responsiveness (promptness and appropriateness of disruption handling), and Adaptability (semantic, spatial, and sequential divergence between original and revised plans). Second, we apply an LLM-as-a-judge approach to automatically assess revision quality. Third, we perform manual expert evaluation to verify whether revisions preserve semantic, spatial, sequential, and responsive aspects. Our experiments show that LLMs maintain strong sequential consistency and semantic stability, while spatial deviations are larger for shorter trips but decrease with longer ones, indicating that extended plans encourage better geographic coherence. However, disruption-handling ability declines as plan length increases, highlighting limits in LLM robustness. TripTide establishes a benchmark for evaluating adaptability, personalization, and resilience in LLM-based travel planning under real-world uncertainty.

  • Open Access

    Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection

    by Ankan Mullick, Saransh Sharma, Abhik Jana, Pawan Goyal

    Ankan Mullick, Saransh Sharma, Abhik Jana, Pawan Goyal. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

  • Open Access

    This is not a Disimprovement: Improving Negation Reasoning in Large Language Models via Prompt Engineering

    by Joshua Jose Dias Barreto, Abhik Jana

    Joshua Jose Dias Barreto, Abhik Jana. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

  • Open Access

    Pruning Literals for Highly Efficient Explainability at Word Level

    by Rohan Kumar Yadav, Bimal Bhattarai, Abhik Jana, Lei Jiao, Seid Muhie Yimam

    Designing an explainable model becomes crucial now for Natural Language Processing(NLP) since most of the state-of-the-art machine learning models provide a limited explanation for the prediction. In the spectrum of an explainable model, Tsetlin Machine(TM) is promising because of its capability of providing word-level explanation using proposition logic. However, concern rises over the elaborated combination of literals (propositional logic) in the clause that makes the model difficult for humans to comprehend, despite having a transparent learning process. In this paper, we design a post-hoc pruning of clauses that eliminate the randomly placed literals in the clause thereby making the model more efficiently interpretable than the vanilla TM. Experiments on the publicly available YELP-HAT Dataset demonstrate that the proposed pruned TM's attention map aligns more with the human attention map than the vanilla TM's attention map. In addition, the pairwise similarity measure also surpasses the attention map-based neural network models. In terms of accuracy, the proposed pruning method does not degrade the accuracy significantly but rather enhances the performance up to 4% to 9% in some test data.

  • Open Access

    CrowdCounter: A benchmark type-specific multi-target counterspeech dataset

    by Punyajoy Saha, Abhilash Datta, Abhik Jana, Animesh Mukherjee

    Counterspeech presents a viable alternative to banning or suspending users for hate speech while upholding freedom of expression. However, writing effective counterspeech is challenging for moderators/users. Hence, developing suggestion tools for writing counterspeech is the need of the hour. One critical challenge in developing such a tool is the lack of quality and diversity of the responses in the existing datasets. Hence, we introduce a new dataset - CrowdCounter containing 3,425 hate speech-counterspeech pairs spanning six different counterspeech types (empathy, humor, questioning, warning, shaming, contradiction), which is the first of its kind. The design of our annotation platform itself encourages annotators to write type-specific, non-redundant and high-quality counterspeech. We evaluate two frameworks for generating counterspeech responses - vanilla and type-controlled prompts - across four large language models. In terms of metrics, we evaluate the responses using relevance, diversity and quality. We observe that Flan-T5 is the best model in the vanilla framework across different models. Type-specific prompts enhance the relevance of the responses, although they might reduce the language quality. DialoGPT proves to be the best at following the instructions and generating the type-specific counterspeech accurately.


  • Open Access

    On Zero-Shot Counterspeech Generation by LLMs

    by Punyajoy Saha, Aalok Agrawal, Abhik Jana, Chris Biemann, Animesh Mukherjee

    With the emergence of numerous Large Language Models (LLM), the usage of such models in various Natural Language Processing (NLP) applications is increasing extensively. Counterspeech generation is one such key task where efforts are made to develop generative models by fine-tuning LLMs with hatespeech - counterspeech pairs, but none of these attempts explores the intrinsic properties of large language models in zero-shot settings. In this work, we present a comprehensive analysis of the performances of four LLMs namely GPT-2, DialoGPT, ChatGPT and FlanT5 in zero-shot settings for counterspeech generation, which is the first of its kind. For GPT-2 and DialoGPT, we further investigate the deviation in performance with respect to the sizes (small, medium, large) of the models. On the other hand, we propose three different prompting strategies for generating different types of counterspeech and analyse the impact of such strategies on the performance of the models. Our analysis shows that there is an improvement in generation quality for two datasets (17%), however the toxicity increase (25%) with increase in model size. Considering type of model, GPT-2 and FlanT5 models are significantly better in terms of counterspeech quality but also have high toxicity as compared to DialoGPT. ChatGPT are much better at generating counter speech than other models across all metrics. In terms of prompting, we find that our proposed strategies help in improving counter speech generation across all the models.

  • Unsupervised Ultra-Fine Entity Typing with Distributionally Induced Word Senses

    by Özge Sevgili, Steffen Remus, Abhik Jana, Alexander Panchenko, Chris Biemann

  • Open Access

    CrowdCounter: A benchmark type-specific multi-target counterspeech dataset

    by Punyajoy Saha, Abhilash Datta, Abhik Jana, Animesh Mukherjee

    Punyajoy Saha, Abhilash Datta, Abhik Jana, Animesh Mukherjee. Proceedings of the 28th Conference on Computational Natural Language Learning. 2024.